Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    list item markers (2. or II.)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.53
     on
    0.47
     عام
    0.47
     et
    0.44
    8
    0.42
    5
    0.41
    াকাল
    0.40
    othic
    0.39
     في
    0.38
     hinzu
    0.38
    POSITIVE LOGITS
    나
    0.54
    ли
    0.49
    u
    0.48
    il
    0.47
    на
    0.47
    ️⃣
    0.46
    다
    0.46
    い
    0.44
    ﻤ
    0.44
     matemático
    0.44
    Act Density 0.295%

    No Known Activations